Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
git clone --depth 1 https://github.com/hoangsonww/AI-News-BriefingWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/plugins/hoangsonww/ai-news-briefing/startup-scout)<a href="https://agentmods.dev/plugins/hoangsonww/ai-news-briefing/startup-scout"><img src="https://agentmods.dev/badge/plugins/hoangsonww/ai-news-briefing/startup-scout/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/plugins/hoangsonww/ai-news-briefing/startup-scout"><img src="https://agentmods.dev/badge/plugins/hoangsonww/ai-news-briefing/startup-scout.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
startup-scout scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
{
"name": "startup-scout",
"description": "Tracks Y Combinator, Product Hunt, and recent VC funding rounds to identify promising early-stage startups in a specific sector.",
"version": "1.0.0",
"author": {
"name": "Research Ops",
"url": "https://github.com/hoangsonww"
},
"homepage": "https://github.com/hoangsonww/AI-News-Briefing",
"repository": {
"type": "git",
"url": "https://github.com/hoangsonww/AI-News-Briefing.git"
},
"license": "MIT",
"keywords": [
"startups",
"vc",
"funding",
"market-research"
],
"categories": [
"business",
"research"
]
}What it installs
The manifest is a name and a version. 1 skill travel with it, and installing the plugin installs all of them — 22 tokens a session between them. Each is measured on its own page, and each can be installed alone.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 9d ago First seen · 25 lines scan A c1b411d3f9d4
startup-scout is a plugin published in the GitHub repository hoangsonww/AI-News-Briefing (41 stars, last pushed yesterday), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other plugins, from other repositories
magician
Full-stack SDLC plugin with dynamic project inspection, a local code knowledge-graph + cache, cross-session reference memory, self-learning, parallel agent orchestration, and feature comprehend→port/integrate (/transmute).
forge
Autonomous spec-driven development loop for Claude Code with behavioral guardrails, knowledge graph integration, and design system support.
seeks
Self-running, verifier-gated loops with durable .seeks/ state and native worktrees.
clone-team
Clone any website with a team of AI agents — pixel-perfect UI clone plus reverse-engineered architecture docs. Built on Claude Code's dynamic Workflow engine with an unskippable test gate; fully pausable and resumable.
loop-engineering
Design production-grade, memory-backed agent loops. Classify deterministic vs non-deterministic, scan your harness (skills/agents/MCP/hooks), derive durable state from the goal, separate done-gates from guardrails, and emit a /loop-ready prompt behind a human approval gate.
g-forge
Educated, enforced project management for AI development - a PM layer, parallel implementation waves, and a git-hook commit gate that can't be skipped. Make any model ship like a senior team.